Table 2 Agreements between algorithm-estimated volume and ground-truth volume of each organ.

From: Fully-automated multi-organ segmentation tool applicable to both non-contrast and post-contrast abdominal CT: deep learning algorithm developed using dual-energy CT images

 

Intraclass correlation coefficient (95% confidence interval)

Training test set

External test set—DECT

External test set—SECT

DE-PVP

VNC

DE-PVP

VNC

SE-PVP

TNC

Liver

0.999 (0.995, 0.999)

0.999 (0.997, 0.999)

0.999 (0.998, 0.999)

0.999 (0.997, 0.999)

0.998 (0.996, 0.999)

0.985 (0.772, 0.996)

Spleen

0.999 (0.996, 0.999)

0.999 (0.996, 0.999)

0.999 (0.998, 0.999)

0.999 (0.997, 0.999)

0.999 (0.998, 0.999)

0.992 (0.984, 0.996)

Right kidney

0.925 (0.697, 0.981)

0.916 (0.660, 0.979)

0.991 (0.957, 0.997)

0.992 (0.984, 0.996)

0.989 (0.961, 0.996)

0.971 (0.816, 0.991)

Left kidney

0.927 (0.704, 0.982)

0.914 (0.653, 0.979)

0.983 (0.884, 0.995)

0.981 (0.935, 0.993)

0.982 (0.839, 0.994)

0.970 (0.454, 0.993)

Pancreas

0.892 (0.566, 0.973)

0.887 (0.546, 0.972)

0.889 (0.689, 0.954)

0.890 (0.395, 0.965)

0.792 (0.231, 0.926)

0.840 (0.694, 0.920)

  1. DECT dual-energy CT, SECT single-energy CT, DE-PVP portal venous phase on dual-energy CT, VNC virtual non-contrast, SE-PVP portal venous phase on single-energy CT, TNC true non-contrast.